Preference-based interactive multi-document summarisation
| Autor: | Iryna Gurevych, Christian M. Meyer, Yang Gao |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Preference learning
Active learning (machine learning) Computer science business.industry media_common.quotation_subject 02 engineering and technology Library and Information Sciences Machine learning computer.software_genre Preference Interactive Learning Ranking (information retrieval) 020204 information systems Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering Reinforcement learning 020201 artificial intelligence & image processing Artificial intelligence Function (engineering) business computer Information Systems media_common |
| Zdroj: | Information Retrieval Journal. 23:555-585 |
| ISSN: | 1573-7659 1386-4564 |
| DOI: | 10.1007/s10791-019-09367-8 |
| Popis: | Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applied, but the existing methods require several thousand interaction rounds even in simulations with perfect user feedback. In this paper, we study preference-based interactive summarisation. To reduce the number of interaction rounds, we propose the Active Preference-based ReInforcement Learning (APRIL) framework. APRIL uses active learning to query the user, preference learning to learn a summary ranking function from the preferences, and neural Reinforcement learning to efficiently search for the (near-)optimal summary. Our results show that users can easily provide reliable preferences over summaries and that APRIL outperforms the state-of-the-art preference-based interactive method in both simulation and real-user experiments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink